Application of the best evacuation model of deep learning in the design of public structures

作者：

Highlights：

• Design and simulation of subway station buildings with deep neural network model

• Comparison of CNN, pre-training and YOLO models with accuracy and training speed

• The accuracy of the model based on YOLO recurrent neural network is the highest.

• Individual differences lead to different evacuation times and satisfaction scores.

摘要

•Design and simulation of subway station buildings with deep neural network model•Comparison of CNN, pre-training and YOLO models with accuracy and training speed•The accuracy of the model based on YOLO recurrent neural network is the highest.•Individual differences lead to different evacuation times and satisfaction scores.

论文关键词：Evacuation,Deep learning,VR video tracking method,YOLO-based recursive neural network model,Simulation

论文评审过程：Received 9 April 2020, Revised 26 May 2020, Accepted 29 June 2020, Available online 12 July 2020, Version of Record 25 July 2020.

论文官网地址：https://doi.org/10.1016/j.imavis.2020.103975